memcp-synthesizer

memcp-synthesizer is an agent for Claude Code from maydali28/memcp. It costs 33 tokens per session (759 once invoked), scanned A, original, MIT.

An agent role for combining findings from several smaller research agents into one checked answer. This is the final “reduce” step in a map-reduce workflow, where separate results are merged.

In plain words
What is it for?
Use it to synthesize multiple mapper outputs into a coherent answer while checking relevance, contradictions, and supporting references.
Why use it?
It filters irrelevant results, identifies disagreements, removes duplication, and keeps track of where findings came from.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions subagents.

Good fit Use it to synthesize multiple mapper outputs into a coherent answer while checking relevance, contradictions, and supporting references.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/maydali28/memcp/memcp-synthesizer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/maydali28/memcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for memcp-synthesizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/maydali28/memcp/memcp-synthesizer.svg)](https://agentmods.dev/agents/maydali28/memcp/memcp-synthesizer)
Your own site
<a href="https://agentmods.dev/agents/maydali28/memcp/memcp-synthesizer"><img src="https://agentmods.dev/badge/agents/maydali28/memcp/memcp-synthesizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 759 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.00759
Opus 5 $0.00016 $0.00380
Sonnet 5 $0.00007 $0.00152
Haiku 4.5 $0.00003 $0.00076

Measured 7d ago against content hash 7d485cfac6ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

memcp-synthesizer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/memcp-synthesizer.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MemCP Synthesizer — RLM Reduce Phase

You are a REDUCE phase sub-agent in the RLM map-reduce pipeline. Your job is to combine findings from multiple mapper sub-agents into a coherent, verified answer.

Your Input

You will receive:

  • question: The original question being answered
  • mapper_outputs: Structured findings from N mapper sub-agents, each containing CHUNK, RELEVANCE, FINDINGS, KEY_QUOTES, and ENTITIES_FOUND

Process

1. ASSESS — Filter and rank mapper outputs

  • Discard any mapper output with RELEVANCE: none
  • Order remaining outputs by relevance (high > medium > low)
  • Note which chunks provided the most useful information

2. DETECT CONTRADICTIONS — Flag disagreements

  • Compare findings across mappers for conflicting information
  • If contradictions exist, note them explicitly
  • Do not silently pick one side — present both with sources

3. SYNTHESIZE — Combine into coherent answer

  • Merge findings from all relevant mappers
  • Deduplicate overlapping information
  • Cite sources: [context_name:chunk_N]
  • Build a complete answer that addresses the original question

4. VERIFY — Cross-reference with the knowledge graph

memcp_recall(query)                  → check against stored insights
memcp_related(insight_id, edge_type) → follow graph edges for context
memcp_search(query)                  → broader search if needed

Cross-reference your synthesized answer with existing knowledge. Flag any discrepancies between mapper findings and stored insights.

5. SAVE — Persist valuable new insights (optional)

If your synthesis produced a genuinely new insight, decision, or finding that would be valuable across sessions, save it:

memcp_remember(
    content="...",
    category="finding",      # or decision, fact, etc.
    importance="medium",     # or high, critical
    tags="relevant,tags",
    entities="entity1,entity2"
)

Only save if the insight is:

  • Non-obvious (not just restating what's in one chunk)
  • Cross-referencing (combines information from multiple sources)
  • Actionable (a decision, finding, or fact worth preserving)

Read the full file on GitHub · 97 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 97 lines · 33 tokens per session scan A 7d485cfac6ce

Subscribe to this mod's changes

memcp-synthesizer is an agent published in the GitHub repository maydali28/memcp (17 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 759 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

executor

Builder to an ALREADY-DECIDED spec (the model split: the main session designs; the executor builds). Use for: building a designed slice/chunk, test writing, mechanical refactors with an objective gate (typecheck, test suites, byte-replay). The spec — normally a file at projects/ /plans/YYYY-MM-DD- .md, named in the…

awrshift/agent-memory-kit · 168 tokens

recon

Read-only fact-gatherer (the model split: the main session designs; recon gathers — breadth over depth). Use for: mapping a codebase surface before a design, input-availability tables, verifying a doc claim against code, sweeping many files for a fact, external fresh-checks against official sources. Returns RAW FACTS…

awrshift/agent-memory-kit · 95 tokens

idea-validator

Isolated Claude instance that critiques ideas, designs, patterns, hypotheses, or plans without context from the parent conversation. Use proactively when a non-trivial design decision needs adversarial review from a fresh perspective. Pair with an external-family model (parallel call) when you have one — different…

awrshift/agent-memory-kit · 97 tokens

qa

QA lens agent: probes the RUNNING product — web UI via Playwright MCP, API via curl/HTTP — through ONE assigned lens (user-flow · edge-state · honesty · contract · ux-critique) and returns STRUCTURED FINDINGS with repro steps + evidence. Observation-only: it never decides, never fixes, never edits files, never clicks…

awrshift/agent-memory-kit · 182 tokens

ryzome-context

Retrieve and summarize Ryzome canvas or document content for context loading.

0xPlaygrounds/ryzome-mcp-plugins · 18 tokens

pydantic-ai-dependency-manager

Dependency and configuration specialist for Pydantic AI agents. USE AUTOMATICALLY after requirements planning to set up agent dependencies, environment variables, model providers, and agent initialization. Creates settings.py, providers.py, and agent.py files.

croakingtoad/context-engineering-mcp · 54 tokens